计算机技术与发展2026，Vol.36Issue(1)：38-45,8.DOI:10.20165/j.cnki.ISSN1673-629X.2025.0195
基于白盒Transformer与动态卷积的弱监督语义分割
Weakly Supervised Semantic Segmentation Based on White Box Transformer and Dynamic Convolution
摘要
Abstract
The weakly supervised semantic segmentation method based on image level labels has attracted much attention because it can train the network with a small number of image level labels to reduce annotation burden.Class activation map generation is a commonly used method in this field,but its quality is limited by the sparsity of initial localization and insufficient feature expression ability.Although existing methods based on visual Transformers optimize class activation maps through self attention,their black box characteristics lead to scattered attention regions,making static convolution difficult to adapt to multi-scale targets,and cross entropy loss is easily dominated by simple samples.To address the aforementioned issues,we propose a weakly supervised semantic segmentation method based on white box Transformer and dynamic convolution.Firstly,a sparse coding white box Transformer module is constructed to generate high-precision class activation maps through interpretable sparse coding mechanisms,effectively suppressing background noise.Secondly,a dynamic conditional convolution module is designed to achieve accurate feature extraction of multi-scale targets by a-daptively adjusting the convolution kernel parameters.Finally,the introduction of Focal Loss improves the segmentation accuracy of the model for difficult to distinguish samples by dynamically suppressing the weights of easily separable samples.Compared to mainstream methods in PASCAL VOC 2012 and MS COCO 2014 validation sets,the proposed method is improved by 1.6 percentage points and 1.3 percentage points in terms of performance,respectively.The experimental results indicate that the model proposed can obtain a more complete class activation graph.关键词
弱监督学习/语义分割/图像级标签/白盒Transformer/动态卷积/类激活图Key words
weakly supervised learning/semantic segmentation/image level labels/white box Transformer/dynamic convolution/class ac-tivation map分类
信息技术与安全科学引用本文复制引用
严格,刘进锋..基于白盒Transformer与动态卷积的弱监督语义分割[J].计算机技术与发展,2026,36(1):38-45,8.基金项目
宁夏自然科学基金(2023AAC03126) （2023AAC03126）
